Using Combinatorial Optimization to Design a High quality LLM Solution

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ackerman, Samuel, Farchi, Eitan, Katan, Rami, Raz, Orna
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929352095039488
author Ackerman, Samuel
Farchi, Eitan
Katan, Rami
Raz, Orna
author_facet Ackerman, Samuel
Farchi, Eitan
Katan, Rami
Raz, Orna
contents We introduce a novel LLM based solution design approach that utilizes combinatorial optimization and sampling. Specifically, a set of factors that influence the quality of the solution are identified. They typically include factors that represent prompt types, LLM inputs alternatives, and parameters governing the generation and design alternatives. Identifying the factors that govern the LLM solution quality enables the infusion of subject matter expert knowledge. Next, a set of interactions between the factors are defined and combinatorial optimization is used to create a small subset $P$ that ensures all desired interactions occur in $P$. Each element $p \in P$ is then developed into an appropriate benchmark. Applying the alternative solutions on each combination, $p \in P$ and evaluating the results facilitate the design of a high quality LLM solution pipeline. The approach is especially applicable when the design and evaluation of each benchmark in $P$ is time-consuming and involves manual steps and human evaluation. Given its efficiency the approach can also be used as a baseline to compare and validate an autoML approach that searches over the factors governing the solution.
format Preprint
id arxiv_https___arxiv_org_abs_2405_13020
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Using Combinatorial Optimization to Design a High quality LLM Solution
Ackerman, Samuel
Farchi, Eitan
Katan, Rami
Raz, Orna
Computation and Language
Artificial Intelligence
We introduce a novel LLM based solution design approach that utilizes combinatorial optimization and sampling. Specifically, a set of factors that influence the quality of the solution are identified. They typically include factors that represent prompt types, LLM inputs alternatives, and parameters governing the generation and design alternatives. Identifying the factors that govern the LLM solution quality enables the infusion of subject matter expert knowledge. Next, a set of interactions between the factors are defined and combinatorial optimization is used to create a small subset $P$ that ensures all desired interactions occur in $P$. Each element $p \in P$ is then developed into an appropriate benchmark. Applying the alternative solutions on each combination, $p \in P$ and evaluating the results facilitate the design of a high quality LLM solution pipeline. The approach is especially applicable when the design and evaluation of each benchmark in $P$ is time-consuming and involves manual steps and human evaluation. Given its efficiency the approach can also be used as a baseline to compare and validate an autoML approach that searches over the factors governing the solution.
title Using Combinatorial Optimization to Design a High quality LLM Solution
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2405.13020